arXiv subjects

Prachi Garg

Publications and source records attributed to Prachi Garg.

7 recordsLinked to original sources

arXiv2026

Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

State-of-the-art vision-language-action (VLA) models such as $\pi_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this finetuning scheme yields strong multi-task policies that, on the target robot, (1) inherit prior tasks distilled from the zero-shot model, (2) enable generalist instruction following, while (3) learning new skills from expert data with improved sample efficiency. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/

cs.RO↗

arXiv2026

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval

Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require, and finding the right frames depends on knowing what to look for. Existing keyframe selectors either score every frame against a single query, or decompose the query into a fixed schema evaluated by a single visual tool. We propose ToolMerge, a keyframe retrieval method based on decomposition and merging: an Large Language Model (LLM) based planner decomposes the query into tool calls and specifies how their per-tool rankings are merged using boolean operators. To evaluate retrieval directly, we construct Molmo-2 Moments (M2M), a benchmark in which every question is anchored to a specific time interval by construction. Across QA, question retrieval, and caption retrieval, ToolMerge is competitive with prior keyframe selectors, most notably on caption retrieval, outperforming other methods by 5%. Code and data can be found at https://github.com/michalsr/ToolMerge .

cs.CV↗

arXiv2025

Hidden Structural Variants in ALD NbN Superconducting Trilayers Revealed by Atomistic Analysis

Microscopic inhomogeneity within superconducting films is a critical bottleneck hindering the performance and scalability of quantum circuits. All-nitride Josephson Junctions (JJs) have attracted substantial attention for their potential to provide enhanced coherence times and enable higher temperature operation. However, their performance is often limited by local variations caused by polymorphism, impurities, and interface quality. This work diagnoses atomic-scale limitations preventing superconducting NbN/AlN/NbN JJs from reaching their full potential. Electrical measurements reveal suppressed critical current density and soft onset of quasiparticle current. However, inverse proportionality between resistance and junction area confirms homogenous barrier thickness. This isolates structural and chemical variations in electrodes and barrier as the source of performance limitation. The observed characteristics are attributed to complex materials problems: NbN polymorphism, phase coexistence, and oxygen impurities. Using advanced microscopy and machine learning integrated approach, nanoscale inclusions of epsilon-Nb2N2 are found to coexist within dominant delta-NbN electrodes. DC performance of JJs may be affected by these defects, leading to unresolved supercurrent and soft transition to normal state. By identifying specific atomic scale defects, tracing its origin to initial film nucleation, and linking to its detrimental electrical signature, this work establishes a material-to-device correlation and provides targeted strategy for phase engineering towards reproducible, high coherence and scalable quantum devices.

quant-ph↗

arXiv2025

All-nitride superconducting qubits based on atomic layer deposition

The development of large-scale quantum processors benefits from superconducting qubits that can operate at elevated temperatures and be fabricated with scalable, foundry-compatible processes. Atomic layer deposition (ALD) is increasingly being adopted as an industrial standard for thin-film growth, particularly in applications requiring precise control over layer thickness and composition. Here, we report superconducting qubits based on NbN/AlN/NbN trilayers deposited entirely by ALD. By varying the number of ALD cycles used to form the AlN barrier, we achieve Josephson tunneling through barriers of different thicknesses, with critical current density spanning seven orders of magnitude, demonstrating the uniformity and versatility of the process. Owing to the high critical temperature of NbN, transmon qubits based on these all-nitride trilayers exhibit microsecond-scale relaxation times, even at temperatures above 300 mK. These results establish ALD as a viable low-temperature deposition technique for superconducting quantum circuits and position all-nitride ALD qubits as a promising platform for operation at elevated temperatures.

quant-ph↗

arXiv2025

Revealing degradation mechanisms in YSZ ceramics through machine learning-guided aging and multiscale characterization

The long-term performance of yttria-stabilized zirconia (YSZ) based energy and biomedical devices is compromised by low-temperature degradation (LTD). This study presents a novel integration of machine learning-guided hydrothermal aging with multiscale characterization to resolve a two-stage degradation mechanism in 3 mol% YSZ. Stage 1 (0 to 30 hrs) features initial surface relief building, which transitions to partial refinement and relief distribution in stage 2 (30 to 60 hrs), alongside a rise in monoclinic phase content. The evolving microstructure increases triple-junction grain boundary density, and these junctions act as degradation hotspots, where vacancy exchange and water access accelerate the transformation. These findings highlight grain boundary chemistry, rather than grain size alone, as a key LTD driver, suggesting boundary engineering as a strategy to enhance YSZ stability for energy, biomedical, and thermal applications.

cond-mat.mtrl-sci↗

arXiv2025

POET: Prompt Offset Tuning for Continual Human Action Adaptation

As extended reality (XR) is redefining how users interact with computing devices, research in human action recognition is gaining prominence. Typically, models deployed on immersive computing devices are static and limited to their default set of classes. The goal of our research is to provide users and developers with the capability to personalize their experience by adding new action classes to their device models continually. Importantly, a user should be able to add new classes in a low-shot and efficient manner, while this process should not require storing or replaying any of user's sensitive training data. We formalize this problem as privacy-aware few-shot continual action recognition. Towards this end, we propose POET: Prompt-Offset Tuning. While existing prompt tuning approaches have shown great promise for continual learning of image, text, and video modalities; they demand access to extensively pretrained transformers. Breaking away from this assumption, POET demonstrates the efficacy of prompt tuning a significantly lightweight backbone, pretrained exclusively on the base class data. We propose a novel spatio-temporal learnable prompt offset tuning approach, and are the first to apply such prompt tuning to Graph Neural Networks. We contribute two new benchmarks for our new problem setting in human action recognition: (i) NTU RGB+D dataset for activity recognition, and (ii) SHREC-2017 dataset for hand gesture recognition. We find that POET consistently outperforms comprehensive benchmarks. Source code at https://github.com/humansensinglab/POET-continual-action-recognition.

cs.CV↗

arXiv2021

Multi-Domain Incremental Learning for Semantic Segmentation

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geographical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain's dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all domains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strategy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plasticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to real-world driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).

cs.CV↗